Loading the data

## New names:
## Rows: 2607 Columns: 20
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (2): Country Name, continent dbl (18): ...1, Year, Agriculture, value added (%
## of GDP), CO2 emissions (me...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`

head(data_frame)
## # A tibble: 6 × 20
##    ...1 `Country Name`  Year Agriculture, value added (…¹ CO2 emissions (metri…²
##   <dbl> <chr>          <dbl>                        <dbl>                  <dbl>
## 1     0 Afghanistan     1962                           NA                 0.0738
## 2     1 Afghanistan     1967                           NA                 0.124 
## 3     2 Afghanistan     1972                           NA                 0.131 
## 4     3 Afghanistan     1977                           NA                 0.183 
## 5     4 Afghanistan     1982                           NA                 0.166 
## 6     5 Afghanistan     1987                           NA                 0.276 
## # ℹ abbreviated names: ¹​`Agriculture, value added (% of GDP)`,
## #   ²​`CO2 emissions (metric tons per capita)`
## # ℹ 15 more variables:
## #   `Domestic credit provided by financial sector (% of GDP)` <dbl>,
## #   `Electric power consumption (kWh per capita)` <dbl>,
## #   `Energy use (kg of oil equivalent per capita)` <dbl>,
## #   `Exports of goods and services (% of GDP)` <dbl>, …

Data Visualization

filtered_data = data_frame |>
  filter(Year == 1962) 
  

filtered_data |>
  select(starts_with('CO2'), gdpPercap) |>
  rename(co2 = starts_with('CO2')) |>
  filter(if_all(everything(), ~ !is.na(.))) |>
  ggplot() +
  geom_point(aes(x = gdpPercap, y = co2)) +
  labs(
    x = 'GDP per capita',
    y = 'CO2 emissions (metric tons per capita)',
    title = 'CO2 emissions per capita generally increases with GDP'
  )

correlation between CO2 emission and GDP growth

correlation_columns = filtered_data |>
  select(starts_with('CO2'), gdpPercap) |>
  rename(co2 = starts_with('CO2')) |>
  filter(if_all(everything(), ~ !is.na(.)))

#since the tow variables are quantitative continuous, i used Pearson correlation
#by default the cor() function will use Pearson method
#the function output a value of 0.9260817 indicating there is a positive relation between the two variables (evolving in the same direction)

cor(correlation_columns$co2,
    correlation_columns$gdpPercap,
    method = 'pearson')
## [1] 0.9260817

#the p_vlaue is used to assess the probability of getting a correlation coefficient as extreme as r, if we sample from a population when the null hypothesis r = 0 is true

cor.test(correlation_columns$co2,
    correlation_columns$gdpPercap,
    method = 'pearson')
## 
##  Pearson's product-moment correlation
## 
## data:  correlation_columns$co2 and correlation_columns$gdpPercap
## t = 25.269, df = 106, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.8934697 0.9489792
## sample estimates:
##       cor 
## 0.9260817

data_frame |>
  select(
    Year,
    co2 = starts_with('CO2'),
    gdpPercap
  ) |>
  filter(!is.na(co2), !is.na(gdpPercap)) |>
  group_by(Year) |>
  summarise(
    r = cor(co2, gdpPercap),
    .groups = 'drop'
  ) |>
  ggplot() +
  geom_bar(aes(x = Year, y = r),
           stat = 'identity') +
  geom_text(aes(x = Year, y = r, label = round(r, 2)),
                vjust = -0.5) +
  scale_x_continuous(breaks = sort(unique(data_frame$Year))) +
  theme(legend.position = 'none')

library(plotly)
## Warning: package 'plotly' was built under R version 4.4.3
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout
plot = data_frame |>
  filter(Year == 1967) |>
  select( co2 = starts_with('CO2'),
          gdpPercap,
          pop,
          continent) |>
  ggplot() +
  geom_point(aes(x = gdpPercap, y = co2, size = pop, color = continent)) +
  scale_x_continuous(
    labels = label_dollar(scale = 1/1000, suffix = 'K')
  ) +
  coord_cartesian(
    xlim = c(0,20000),
    ylim = c(0,25)
  ) +
  labs(
    x = 'GDP per capita',
    y = 'CO2 emissions (metric tons per capita)'
    )

ggplotly(plot)